Claude Science, an AI workbench for scientists

Summary

Claude Science is a beta AI workbench for scientists that brings databases, research tools, computing resources, and domain-specific workflows into one environment. Researchers can analyze literature, run multi-step studies, create figures and manuscripts, and revise them through conversation. Every generated artifact includes its code, environment, plain-language creation description, and message history, while a reviewer agent checks citations, calculations, and consistency between figures and code. A coordinating agent uses more than 60 curated skills and connectors across fields including genomics, single-cell, proteomics, structural biology, and cheminformatics; it can manage jobs on local systems, HPC clusters over SSH, or Modal, scaling from one GPU to hundreds. Beta access is available on macOS and Linux for Pro, Max, Team, and Enterprise users, with reported examples including faster glioma analyses and large literature reviews.

Takeaways

1. 1

   Generated figures and manuscripts include the exact code and environment used, a plain-language creation description, and the full message history, supporting later validation and reproduction.

2. 2

   Claude Science can ask before accessing new resources and submit jobs to an existing HPC cluster over SSH or to Modal, scaling analyses from a single GPU to hundreds.

3. 3

   A beta workflow at the Allen Institute produced about 10 long reviews with reviewer-checked citations, while one UCSF lab reported comprehensive germline analyses in roughly one-tenth of the previous time and independently validated the results.